Associative memory model with arbitrary Hebbian length

Abstract

Conversion of temporal to spatial correlations in the cortex is one of the most intriguing functions in the brain. The learning at synapses triggering the correlation conversion can take place in a wide integration window, whose influence on the correlation conversion remains elusive. Here, we propose a generalized associative memory model with arbitrary Hebbian length. The model can be analytically solved, and predicts that a small Hebbian length can already significantly enhance the correlation conversion, i.e., the stimulus-induced attractor can be highly correlated with a significant number of patterns in the stored sequence, thereby facilitating state transitions in the neural representation space. Moreover, an anti-Hebbian component is able to reshape the energy landscape of memories, akin to the function of sleep. Our work thus establishes the fundamental connection between associative memory, Hebbian length, and correlation conversion in the brain.

arXiv comment6 pages, 2 figures

References in corpus (7)

• Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rules
• A Moving Bump in a Continuous Manifold: A Comprehensive Study of the Tracking Dynamics of Continuous Attractor Neural Networks
• Extended temporal association memory by inhibitory Hebbian learning
• Capacity-resolution trade-off in the optimal learning of multiple low-dimensional manifolds by attractor neural networks
• Minimal model of permutation symmetry in unsupervised learning
• Statistical physics of unsupervised learning with prior knowledge in neural networks
• Eigenvalue spectrum of neural networks with arbitrary Hebbian length

Cited by in corpus (4)

• Spectrum of non-Hermitian deep-Hebbian neural networks
• Emergence of hierarchical modes from deep learning
• Eigenvalue spectrum of neural networks with arbitrary Hebbian length
• Theory of Critical Phenomena with Memory